1bb7993a97
Fix MSVC ARM64 build. Add generic kernel for ARM64
2022-06-02 16:53:54 +02:00
dc49edd4e6
Revert "roll back DGEMM kernel ... for DYNAMIC_ARCH"
2022-05-20 11:23:30 +02:00
b62173c5a0
POWER10: Changing store instructions for Level1 functions
...
This patch changes 32 bytes stores to two 16 bytes stores
to fix a recent degradation due to 32 bytes stores.
2022-05-12 11:17:33 -05:00
84cb58b7fb
Fix generator rules for ?laswp_ncopy and ?neg_tcopy
2022-04-30 15:28:38 +02:00
05dcfa176e
fix undefined prefetchsizes
2022-04-16 10:04:27 +02:00
2bbb9f05c7
fix undefined prefetchsize
2022-04-16 10:00:10 +02:00
115bc9b98f
CortexX1 is ARMV8 like A7x
2022-03-28 17:28:29 +02:00
b3b4672c30
Add initial support for Phytium FT2000 series and ARMV9 Cortex 510/710/X1/X2
2022-03-27 15:29:20 +02:00
40302558ed
Remove extraneous (and wrong) definition of sbgemm_r on x86_64
2022-03-23 20:05:32 +01:00
5cc1111383
fix unsafe read of Y in assembly kernel
2022-03-11 11:56:33 -06:00
45786b05da
Merge branch 'develop' into risc-v
2022-02-28 11:48:02 +08:00
225683218c
Small Matrix: use proper inline asm input constraint for AVX512 mask
2022-02-28 03:22:31 +00:00
9c626e466e
really fix definition of SHUFFLE_MAGIC_NO
2022-02-25 15:36:02 +01:00
0698212c8c
Remove stray $
2022-02-25 15:33:02 +01:00
9d7429406f
Declare SHUFFLE_MAGIC_NO as const to placate clang
2022-02-25 10:05:36 +01:00
d9894f45d3
Define sbgemm_r to fix DYNAMIC_ARCH builds
2022-02-25 10:04:00 +01:00
522f809825
Merge pull request #3542 from martin-frbg/issue3540
...
Fix compilation for CooperLake on Windows/clang
2022-02-24 00:00:00 +01:00
abbc947edb
Fix compilation of Skylake AVX512 kernels with GCC 6
2022-02-23 22:51:59 +00:00
c62f8e2c01
Prevent compiler attempts to use k0 as mask register
2022-02-23 20:12:20 +01:00
80eb581c83
Fix non-portable u_int64_t
2022-02-23 20:10:59 +01:00
73ffabe6ba
Guard uses of _mm512_reduce_add_p?
2022-02-23 20:06:14 +01:00
7656aba00e
Merge pull request #3493 from martin-frbg/casts+cleanup
...
WIP casts and cleanups
2022-02-06 23:55:06 +01:00
addc2a7aaa
Add proper defaults for IMIN/IMAX
2022-01-27 19:56:32 +01:00
299d4d70a3
Add default KERNEL file for Elbrus E2K arch
2022-01-22 18:59:36 +01:00
3492bea602
Create Makefile
2022-01-22 18:57:28 +01:00
898cf5faf3
Add Elbrus e2k architecture support
2022-01-22 18:55:10 +01:00
c1c0d5ce1d
Merge pull request #3492 from binebrank/arm_sve_zgemm
...
SVE zgemm&cgemm (and other BLAS 3 complex)
2022-01-18 21:36:33 +01:00
19d435b1b3
update armv8sve + contributors
2022-01-18 08:28:31 +01:00
f158d59087
adapt CMake
2022-01-17 22:36:48 +01:00
b6a445cfd8
adapt Makefile for SVE trsm
2022-01-16 21:40:56 +01:00
0fb6cc07bf
fix ztrsm lt/ut copy
2022-01-16 21:39:57 +01:00
f1315288a8
add sve ztrsm
2022-01-15 22:27:25 +01:00
aaa2b1a861
fix sve dtrsm kernels
2022-01-15 21:02:14 +01:00
8071e179f1
add remaining sve trsm copy kernels
2022-01-11 21:16:38 +01:00
f87468ac91
trsm_lncopy_sve
2022-01-10 21:45:37 +01:00
e8939b3d30
sve trsmRN and trsmRT
2022-01-10 20:42:20 +01:00
098672b51b
add trsm_kernel_LT_sve
2022-01-09 20:11:47 +01:00
be7e55880c
sve trsm_kernel_LN
2022-01-09 19:40:04 +01:00
b6b024232d
Merge pull request #3508 from snadampal/v1_n2
...
OpenBLAS: aarch64: Add neoverse-v1/n2 architecture specifics
2022-01-09 14:50:26 +01:00
19c8f615dc
OpenBLAS: aarch64: Add neoverse-v1/n2 architecture specifics
2022-01-07 00:28:17 +00:00
bb33446b40
fix makefile.L3
2022-01-06 10:26:11 +01:00
f33543d029
combine zchemm into single file
2022-01-05 14:42:37 +01:00
0c91d043ae
adapt CMake for SVE
2022-01-05 14:36:39 +01:00
39ab219704
sve copy functions for cgemm chemm zsymm
2022-01-05 09:12:22 +01:00
18102ae8c3
add cgemm ctrmm sve kernels
2022-01-05 09:09:18 +01:00
87537b8c55
modify sve zgemmcopy kernels
2022-01-05 09:07:28 +01:00
d30157d891
update configuration of kernels for A64FX and ARMV8SVE
2022-01-05 09:00:54 +01:00
07fa6fa3b1
configure Makefile for sve
2022-01-05 08:57:51 +01:00
2e2c02b762
fix sve ztrmm kernel
2022-01-04 14:42:07 +01:00
68c414d3a6
ztrmm sve copy functions
2022-01-04 14:40:59 +01:00
ce329ab686
add sve zhemm copy routines
2022-01-03 15:56:05 +01:00
0140373802
add sve ztrmm
2022-01-02 19:15:33 +01:00
f7b6912868
ztrmm sve copy kernels
2021-12-30 21:00:16 +01:00
40b14e4957
fix zgemm kernel
2021-12-29 11:42:04 +01:00
6ec4aab875
zgemm sve copy routines
2021-12-26 17:05:46 +01:00
878064f394
sve zgemm kernel
2021-12-26 08:44:05 +01:00
683a7548bf
added macros for sve zgemm kernels
2021-12-25 11:46:41 +01:00
7b146e590c
fix function typecast
2021-12-24 20:01:52 +01:00
e9a0e52201
fix function typecast
2021-12-24 20:00:50 +01:00
d1ee6ff73f
fix function typecasts
2021-12-21 18:45:28 +01:00
e3c9947c0f
prepare kernel for sve zgemm
2021-12-21 11:19:27 +01:00
8d9b9c6b2a
loongarch64: Optimize dgemm_kernel
2021-12-21 09:33:06 +08:00
92b7b949dd
fix bug in zscal function
...
memset can not be used in zscal because of
the stride parameters.
Signed-off-by: Wu Zhigang <zhigang.wu@starfivetech.com>
2021-12-15 01:23:30 -08:00
b0a590f4fe
Merge pull request #3475 from wjc404/optimize-A53-dgemm
...
optimize cgemm on ARM cortex A53 & cortex A55
2021-12-12 19:09:08 +01:00
f4d1f0333b
Merge pull request #3474 from rafaelcfsousa/rafael/cmake_power
...
Add CMake support for Power
2021-12-12 19:08:27 +01:00
b610d2de37
optimize cgemm on ARM cortex A53 & cortex A55
2021-12-12 17:22:52 +08:00
697e2752d7
Merge pull request #3464 from binebrank/arm_sve_sgemm
...
Add sgemm part for Arm SVE
2021-12-11 20:35:22 +01:00
a8f62a347b
fix UNROLL_MN and add to targets for SVE
2021-12-11 16:37:23 +01:00
774267fdac
adjust Makefile.L3 for SVE
2021-12-11 16:35:08 +01:00
23a7561353
Fix error cmake (small kernels)
2021-12-09 09:57:39 -06:00
5378046abd
roll back DGEMM kernels to 4x8 when compiling for DYNAMIC_ARCH
2021-12-06 19:43:54 +01:00
a1fea1fe2a
sgemm v2x8 SVE kernel
2021-12-05 18:47:29 +01:00
abe1ce3434
strmm sve v1x8 kernel
2021-12-05 14:03:08 +01:00
54d321d742
Merge pull request #3466 from rafaelcfsousa/rafael/small_matrix_p10
...
[POWER] Add small matrix for sgemm/dgemm on Power10
2021-12-03 12:12:20 +01:00
0882db30a2
Merge pull request #3455 from cenewcombe/develop
...
Fix unsafe read during final iteration of zsymv_L_sse2.S
2021-12-03 10:01:20 +01:00
0de36f7b5c
trmm sve copy fucntions for single precision
2021-11-29 21:25:05 +01:00
c78fdcc80d
[POWER] Add support for SMALL_MATRIX_OPT
2021-11-28 12:41:16 -06:00
86ae89bf33
add sgemm kernel and copy functions for sgemm and ssymm
2021-11-28 18:12:47 +01:00
454edd741c
Merge pull request #3425 from binebrank/arm_sve_dgemm
...
Add dgemm kernel for arm64 SVE
2021-11-26 16:14:55 +01:00
bcfbdc81b2
Merge pull request #3459 from rafaelcfsousa/fix_cmake
...
Fix issues when building OpenBLAS with cmake
2021-11-26 15:19:24 +01:00
1af73ce38e
Adapt CMake for SVE
2021-11-26 10:35:01 +01:00
e7fca060db
Merge pull request #3457 from wjc404/optimize-A53-dgemm
...
MOD: optimize zgemm on cortex-A53/cortex-A55
2021-11-26 10:30:47 +01:00
5c1cd5e0c2
MOD: add comments to a53 zgemm kernel
2021-11-25 22:48:48 +08:00
d5c9353f1b
Modify the order that cmake set the KERNEL variables (generic now is fallback)
2021-11-24 20:08:35 -06:00
9f59b19fcd
MOD: optimize zgemm on cortex-A53/cortex-A55
2021-11-24 21:51:45 +08:00
531a28b6a0
removed unused code (compiler warnings)
2021-11-22 10:12:34 +01:00
9b9cb90bb1
modify Makefile for SVE copy
2021-11-22 09:54:20 +01:00
9388f05a3c
configure SVE Makefile
2021-11-21 18:33:43 +01:00
b58d4f31ab
some clean-up & commentary
2021-11-21 14:56:27 +01:00
b7df500106
Add generic mips32 target
2021-11-20 17:31:51 +01:00
e6ed4be02e
symm SVE copy rutines
2021-11-20 16:35:29 +01:00
feeb8283a5
Fix unsafe read during final iteration of zsymv_L_sse2.S
2021-11-19 14:29:32 -06:00
302f22693a
MOD: optimize normal DGEMM on ARMV8 cortex-A53 & cortex-A55
2021-11-18 21:14:43 +08:00
3c7eed0e53
add remaining trmm copy rutines for SVE
2021-11-14 16:00:10 +01:00
7d996b1c36
dtrmm_utcopy sve function
2021-11-13 18:48:53 +01:00
ab7917910d
add v2x8 kernel + fix sve dtrmm
2021-11-07 20:37:51 +01:00
7093372e32
add ARMV8SVE target
2021-11-01 22:53:21 +01:00
a8fbdbac34
fix sve dgemm kernel + sve dtrmm
2021-10-31 10:24:25 +01:00
746b4f0f17
added SVE ncopy and tcopy
2021-10-30 12:11:44 +02:00
1a10d3e09d
add sve dgemm prototype
2021-10-27 16:37:18 +02:00
22bf5c27ba
Add basic support for the Fujitsu A64FX ( #3415 )
...
* Add initial support for Fujitsu A64FX as generic ARMV8
2021-10-18 15:00:19 +02:00
63a103ba6e
sbgemm: spr: disable small matrix path by default
2021-10-17 19:08:03 -07:00
82194ea9d2
sbgemm: spr: implement otcopy_16
2021-10-17 19:08:03 -07:00
8632380a96
sbgemm: spr: reuse ncopy_16 from cooperlake as incopy
2021-10-17 19:08:03 -07:00
6bc8204ce5
sbgemm: spr: optimization for tmp_c buffer
2021-10-17 19:08:03 -07:00
f018aa342a
sbgemm: spr: kernel handle alpha != 1.0
2021-10-17 19:08:03 -07:00
a52456b168
sbgemm: spr: oncopy: use tile load/store instead
2021-10-17 19:08:03 -07:00
f2485352a6
sbgemm: spr: only load A once in tail_k handling
2021-10-17 19:08:03 -07:00
9ab33228bb
sbgemm: spr: process k2 and odd k at the same time
2021-10-17 19:08:03 -07:00
10d52646e2
sbgemm: spr: oncopy: avoid handling too much pointer at a time
2021-10-17 19:08:03 -07:00
88154ed02d
sbgemm: spr: reduce tile conf loading by seperate tail k handling
2021-10-17 19:08:03 -07:00
a70bfb52d5
sbgemm: spr: kernel works for NN case when alpha is 1.0
2021-10-17 19:08:03 -07:00
6051c86741
sbgemm: spr: kernel works for m32 in NN case
2021-10-17 19:08:03 -07:00
d0b253ac6e
sbgemm: spr: implement oncopy_16
2021-10-17 19:08:03 -07:00
1d48b7cb16
sbgemm: spr: add dummy source files
2021-10-17 19:08:03 -07:00
3dc6052c7e
initial support for Sapphire Rapids platform
2021-10-12 01:30:40 -07:00
8c20ca345a
Use Neoverse's current mix of ThunderX2 kernels for Vortex as well
2021-10-06 11:06:43 +02:00
8e4c209002
Merge pull request #3398 from kavanabhat/aix_p10_gnuas
...
Big Endian Changes for Power10 kernels
2021-10-05 18:59:47 +02:00
9cc95e5657
AIX changes for P10 with GNU Compiler
2021-10-01 05:18:35 -05:00
fe3c778c51
AIX changes for P10 with GNU Compiler
2021-09-30 06:06:27 -05:00
ee5ca8a328
x86_64: BFLOAT16: fix build warning
2021-09-28 18:30:06 +08:00
90cc944625
Move alphaI to x22 to leave x18 unused (reserved on OSX)
2021-09-17 09:53:18 +02:00
590fbff06e
move alpha to x19/x20 to leave x18 unused for OSX
2021-09-17 09:42:17 +02:00
380940271b
Move temp to x21 to leave x18 unused (reserved on OSX)
2021-09-17 09:28:19 +02:00
7d75177446
Move temp to x21 to leave x18 unused (reserved on OSX)
2021-09-17 09:24:11 +02:00
0a4ac4b585
Use x21 for I to leave x18 unused (reserved on OSX)
2021-09-17 09:19:51 +02:00
7d4a221579
Remove unused TEMP2 and reshuffle to leave x18 unused (reserved on OSX)
2021-09-17 09:18:25 +02:00
d3a9c7ef7f
Merge pull request #3382 from rafaelcfsousa/rafael/cwarnings
...
[POWER] Remove unused variable warnings.
2021-09-17 09:15:16 +02:00
8dfa61a61c
Initialize abs_mask1 with itself to silence a gcc warning
2021-09-15 22:11:35 +02:00
99aa10b3ff
Initialize abs_mask1 with itself to silence a gcc warning
...
actual initialization is via the _mm_cmpeq_ep18, which I've seen claimed to be the fastest way to set an xmm register to all 1s
2021-09-15 22:10:43 +02:00
b751edf624
Fix unused variable warnings on Power
2021-09-15 13:36:07 -05:00
80346b8813
Merge pull request #3379 from martin-frbg/issue3369-2
...
Add casts to fix compiler warnings for SkylakeX sasum/dasum
2021-09-15 07:18:57 +02:00
ce036a2fc0
Add casts
2021-09-14 21:41:53 +02:00
ddf106f769
Add dedicated entries for BFLOAT16 kernels
2021-09-14 16:17:18 +02:00
af8843875a
Merge pull request #3376 from martin-frbg/issue3370
...
Fix a few harmless compiler warnings
2021-09-12 00:01:31 +02:00
0925dfe2c9
One instance of kernel_4x1 is used even on SKX
2021-09-11 15:30:19 +02:00
7d873a329f
Add ifdefs around conditionally used functions
2021-09-11 14:38:47 +02:00
ef24712030
Move a conditionally used variable
2021-09-11 14:37:44 +02:00
d17238599b
Add casts
2021-09-11 13:38:28 +02:00
59a1114d03
sbgemm: cooperlake: tuning for small matrix
2021-09-07 21:30:46 +08:00
682d66555d
sbgemm: cooperlake: implement ncopy_16
2021-09-07 21:30:46 +08:00
beccb83b16
sbgemm: cooperlake: add n24 kernel for tcopy_4
2021-09-07 21:30:46 +08:00
5fcacad32b
sbgemm: cooperlake: implement tcopy_4
2021-09-07 21:30:46 +08:00
bb1c4fa5bd
sbgemm: cooperlake: prefetch A & B
2021-09-07 21:30:46 +08:00
7a2d1601ec
sbgemm: cooperlake: unroll core loop by 2
2021-09-07 21:30:46 +08:00
45fdf951b6
sbgemm: cooperlake: reorder ptr increase for performance
2021-09-07 21:30:46 +08:00
cece3541ab
sbgemm: cooperlake: fix bug in m64n12
2021-09-07 21:30:46 +08:00
9df0953cde
sbgemm: cooperlake: kernel works for NN
2021-09-07 21:30:45 +08:00
2ec9f3a8aa
sbgemm: cooperlake: change kernel size to 16x4
2021-09-07 21:30:45 +08:00
ef8f5fecc8
sbgemm: cooperlake: implement sbgemm_tcopy_32
2021-09-07 21:30:45 +08:00
4c294336e6
sbgemm: cooperlake: add dummy source files
2021-09-07 21:30:45 +08:00
f1e3305974
Add workaround for Windows10 macro name clash
2021-09-01 21:36:50 +02:00
619588fbab
sbgemm: remove unnecessary b0 files
2021-08-30 17:55:01 +08:00
f39301935c
sbgemm: cooperlake: make sure hot buffer aligned to 64
2021-08-30 17:40:30 +08:00
7d27b182fc
sbgemm: cooperlake: enable SBGEMM by small matrix path
2021-08-30 17:40:30 +08:00
1d83ca4bca
Small Matrix: support BFLOAT16 data type
2021-08-30 17:40:20 +08:00
bec9d9f63d
Merge pull request #3335 from guowangy/small-matrix-latest
...
Add GEMM optimization for small matrix and single/double kernel for skylakex
2021-08-29 22:33:33 +02:00
dbbb39199f
sgemv: skylakex: fix build warning
2021-08-25 07:13:00 +00:00
e9acb46431
sgemv: skylakex: bug fix for sgemv_t kernel in corner case
2021-08-25 07:07:27 +00:00
f9dba63c28
Small Matrix: skylakex: remove unnecessary b0 source files
2021-08-13 03:28:44 +00:00
989e6bbdd3
Small Matrix: reduce generic kernel source files
2021-08-13 03:17:38 +00:00
04255be948
Merge pull request #3344 from gxw-loongson/develop
...
Delete the macro instruction "li" and use "li.d" instead
2021-08-12 15:16:46 +02:00
a7bc8ec1f1
Delete the macro instruction "li" and use "li.d" instead
...
Change-Id: Icff7981e2eb7df29ba5af1f8eb5be8443c67450f
2021-08-12 17:02:54 +08:00
b06880c2cd
POWER10: Improving dasum performance
...
Unrolling a loop in dasum micro code to help in improving
POWER10 performance.
2021-08-10 22:06:04 -05:00
44d0032f3b
Small Matrix: skylakex: fix build error in old compiler
2021-08-05 04:43:47 +00:00
5d86becdae
Add all SBGEMM kernels for IA AVX512-BF16 based platforms
...
Added all SBGEMM kernels including NN/NT/TN/TT for both ColMajor and
RowMajor, based on AVX512-BF16 ISA set on IA.
Signed-off-by: Chen, Guobing <guobing.chen@intel.com>
2021-08-05 11:11:29 +08:00
fee5abd84b
Small Matrix: support cmake build
2021-08-04 08:50:15 +00:00
478d1086c1
Small Matrix: support DYNAMIC_ARCH build
2021-08-04 03:12:41 +00:00
6b58bca18b
Small Matrix: disable low performance default kernel
2021-08-03 06:49:03 +00:00
fa777f5517
Small Matrix: skylakex: add DGEMM_SMALL_M_PERMIT and tune for TN kernel
2021-08-02 07:06:54 +00:00
8592c21af4
Small Matrix: skylakex: dgemm nn: fix typo in idx load
2021-08-02 07:06:54 +00:00
3e79f6d89a
Small Matrix: skylakex: add dgemm tn kernel
2021-08-02 07:06:54 +00:00
323d7da4f7
Small Matrix: skylakex: add dgemm tt kernel
2021-08-02 07:06:54 +00:00
f57fc932ac
Small Matrix: skylakex: add dgemm nt kernel
2021-08-02 07:06:54 +00:00
91ec21202b
Small Matrix: skylakex: add dgemm nn kernel
2021-08-02 07:06:54 +00:00
72e070539c
Small Matrix: skylakex: add sgemm tt kernel
2021-08-02 07:06:54 +00:00
02c6e764f2
Small Matrix: skylakex: add SGEMM_SMALL_M_PERMIT and tune for TN kernel
2021-08-02 07:06:54 +00:00
5dc7c3c8e5
Small Matrix: add GEMM_SMALL_MATRIX_PERMIT to tune small matrics case
2021-08-02 07:06:54 +00:00
642c393879
Small Matrix: skylakex: add sgemm tn kernel
2021-08-02 07:06:54 +00:00
ae3f5c737c
Small Matrix: skylakex: sgemm nt: optimize for M < 12
2021-08-02 07:06:54 +00:00
0d72d75bf9
Small Matrix: skylakex: add sgemm nt kernel
2021-08-02 07:06:54 +00:00
ca7682e3a3
Small Matrix: skylakex: sgemm nn: fix n6 conflicts with n4
2021-08-02 07:06:54 +00:00
9967e61abb
Small Matrix: skylakex: sgemm nn: fix error when beta not zero
2021-08-02 07:06:54 +00:00
a87736346f
Small Matrix: skylakex: sgemm nn: add n6 to improve performance
2021-08-02 07:06:54 +00:00
4c9d9940fd
Small Matrix: skylakex: sgemm nn: reduce store 4 N at a time
2021-08-02 07:06:54 +00:00
13b32f69b7
Small Matrix: skylakex: sgemm nn: reduce store 4 M at a time
2021-08-02 07:06:54 +00:00
3d8c6d9607
Small Matrix: skylakex: sgemm nn: clean up unused code
2021-08-02 07:06:54 +00:00
49b61a3f30
Small Matrix: skylakex: sgemm_nn: optimize for M <= 8
2021-08-02 07:06:54 +00:00
f88470323b
Optimize M < 16 using AVX512 mask
2021-08-02 07:06:54 +00:00
9186456a12
small matrix: SkylakeX: add SGEMM NN kernel
2021-08-02 07:06:54 +00:00
6022e5629c
Refs #2587 fix small matrix c/zgemm bug.
2021-08-02 07:06:54 +00:00
57ed58cefe
Refs #2587 Add small matrix optimization reference kernel for c/zgemm.
2021-08-02 07:06:54 +00:00
17d32a4a82
Change a1b0 gemm to b0 gemm.
2021-08-02 07:06:54 +00:00
59cb5de46b
Refs #2587 Fix typos.
2021-08-02 07:06:54 +00:00
be3349405d
Add alpha=1.0 beta=0.0 for small gemm.
2021-08-02 07:01:47 +00:00
0a2077901c
Add small marix optimization kernel interface.
...
make SMALL_MATRIX_OPT=1
2021-08-02 07:01:47 +00:00
0b8f7c8c10
Add cmake support for LOONGARCH64
2021-08-02 10:00:41 +08:00
af0a69f355
Add support for LOONGARCH64
2021-07-27 15:29:12 +08:00
49bbf330ca
Empirical workaround for numpy SVD NaN problem from issue 3318
2021-07-18 22:19:19 +02:00
5b4b385ecf
Temporarily disable the SkylakeX sgemv_t microkernel due to LAPACK testsuite failures
2021-07-14 20:50:14 +02:00
Nursultan Zarlyk
Martin Kroeker
Rajalakshmi Srinivasaraghavan
Caroline Newcombe
Xianyi Zhang
Wangyang Guo
Mosè Giordano
Bine Brank
Sunita Nadampalli
gxw
Wu Zhigang
Jia-Chen
Rafael Cardoso Fernandes Sousa
kavanabhat
gxw
Chen, Guobing